# Short Answer Question Answering on Natural Questions (NQ) (test)

Source: [Short Answer Question Answering on Natural Questions (NQ) (test)](<https://www.sota2.com/research/sota/short-answer-question-answering-on-natural-questions-nq-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-12T07:24:43.301Z

Evaluation of model performance on the test split of the Natural Questions (NQ) dataset, focusing on Short Answer Question Answering using Precision, Recall, and F1 scores.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Short Answer Question Answering |
| Dataset (including any stated split) | Natural Questions (NQ) (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [F1 Score](<https://www.sota2.com/research/sota/short-answer-question-answering-on-natural-questions-nq-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/short-answer-question-answering-on-natural-questions-nq-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/short-answer-question-answering-on-natural-questions-nq-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [Rank](<https://www.sota2.com/research/sota/short-answer-question-answering-on-natural-questions-nq-test.md?metric=Rank>): Lower is better; unit: SCALAR.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| AGAR | 67.4 | Not recorded | 6a2b92b7d33dfb23e783b14d |
| RikiNet | 61.3 | Not recorded | 68fa6a211e209131cea262e2 |
| Cluster-Former | 60.9 | Not recorded | 68fa6a211e209131cea262e2 |
| VEA-Con | 59.9 | Not recorded | 6a2b92b7d33dfb23e783b14d |
| Uniform | 59.6 | Not recorded | 6a2b92b7d33dfb23e783b14d |
| Random | 59.3 | Not recorded | 6a2b92b7d33dfb23e783b14d |
| Plain VQA | 59.1 | Not recorded | 6a2b92b7d33dfb23e783b14d |
| VEA-Br | 59 | Not recorded | 6a2b92b7d33dfb23e783b14d |
| BigBird-ETC-large | 57.9 | Not recorded | 68fa6a211e209131cea262e2 |
| ETC | 57.86 | Not recorded | 68fa689c1e209131cea1d06b |
| AGLA | 53 | Not recorded | 6a2b92b7d33dfb23e783b14d |
| VAR | 52.4 | Not recorded | 6a2b92b7d33dfb23e783b14d |
| BERT joint | 52.1 | Not recorded | 68fa66ce1e209131cea127dc |
| DocumentQA | 35.1 | Not recorded | 68fa66ce1e209131cea127dc |
| CGR | 33.6 | Not recorded | 6a2b92b7d33dfb23e783b14d |
| DecAtt + DocReader | 31.5 | Not recorded | 68fa66ce1e209131cea127dc |

### AGAR

F1 Score: 67.4. Result ID: 6a2bb42ffbc373592c29b149.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction.

### RikiNet

F1 Score: 61.3. Result ID: 698e12edffc3901de09a9646.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea262e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676f1e209131cea16356.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Cluster-Former

F1 Score: 60.9. Result ID: 698e12edffc3901de09a9647.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea262e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea262e2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### VEA-Con

F1 Score: 59.9. Result ID: 6a2bb42ffbc373592c29b145.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5e1e209131cea8dc51.md>)

Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction.

### Uniform

F1 Score: 59.6. Result ID: 6a2bb42ffbc373592c29b143.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction.

### Random

F1 Score: 59.3. Result ID: 6a2bb42ffbc373592c29b142.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction.

### Plain VQA

F1 Score: 59.1. Result ID: 6a2bb42ffbc373592c29b141.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction.

### VEA-Br

F1 Score: 59. Result ID: 6a2bb42ffbc373592c29b144.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5e1e209131cea8dc51.md>)

Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction.

### BigBird-ETC-large

F1 Score: 57.9. Result ID: 698e12edffc3901de09a9645.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea262e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690b1e209131cea1faf6.md>)

[Implementation](<http://goo.gle/bigbird-transformer>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ETC

F1 Score: 57.86. Result ID: 698d78a68b517eb43321be7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa689c1e209131cea1d06b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa689c1e209131cea1d06b.md>)

[Implementation](<http://goo.gle/research-etc-model>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AGLA

F1 Score: 53. Result ID: 6a2bb42ffbc373592c29b148.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea7376d.md>)

Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction.

### VAR

F1 Score: 52.4. Result ID: 6a2bb42ffbc373592c29b147.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77821e209131cea73b60.md>)

Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction.

### BERT joint

F1 Score: 52.1. Result ID: 698d092a8b517eb4331e8671.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ce1e209131cea127dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66ce1e209131cea127dc.md>)

[Implementation](<https://github.com/google-research/language/tree/master/language/question_answering/bert_joint>)

Recorded evaluation configuration: {"pre-training":"SQuAD 1.1 fine-tuned"}. This record does not assert independent reproduction.

### DocumentQA

F1 Score: 35.1. Result ID: 698d092a8b517eb4331e866f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ce1e209131cea127dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00e26.md>)

[Implementation](<https://www.sota2.com/github.com/allenai/document-qa>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CGR

F1 Score: 33.6. Result ID: 6a2bb42ffbc373592c29b146.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92b7d33dfb23e783b14d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77821e209131cea73b60.md>)

Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction.

### DecAtt + DocReader

F1 Score: 31.5. Result ID: 698d092a8b517eb4331e8670.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ce1e209131cea127dc.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
